2020 · 15 citations · 7 references
ManagementData ScienceElectrical EngineeringEnergy ManagementEnergy SystemsSensor FusionBuilding AutomationElectricity Load ManagementEnergy Demand ForecastingEnergy MeteringEnergy UseLoad ForecastingActivity RecognitionBenchmark DatasetsElectricity Consumption ForecastingGround Truth Data CollectionHuman Activity RecognitionLightingResidential Load ForecastingSmart Metering
As more and more homes are equipped with smart electricity meters, home owners gain the ability to monitor their total electricity consumption on a daily or hourly basis. Techniques such as load forecasting, load disaggregation, and activity recognition try to provide even better insights into our electricity consumption, highlight saving potential or improve our daily living. To develop and evaluate these techniques, publicly available datasets are used. We identified a lack of high frequency fully labeled electricity datasets in the residential domain and present the FIRED dataset. It contains 52 days of 8 kHz aggregated current and voltage readings of the 3-phase supply of a typical residential apartment in Germany. The dataset also contains synchronized ground truth data as 2 kHz readings of 21 individual appliances, as well as room temperature readings and fully labeled state changes of the lighting system, resulting in a complete and versatile residential electricity dataset.
7
Nonintrusive appliance load monitoring
George Hart · Proceedings of the IEEE · 1992 · 3.1K citations
Nipun Batra, Jack Kelly, Oliver Parson et al. · 2014 · 488 citations · Full text
The ECO data set and the performance of non-intrusive load monitoring algorithms
Christian Beckel, Wilhelm Kleiminger, Romano Cicchetti et al. · 2014 · 336 citations